A computer-aided determining method for the myometrial infiltration depth of early endometrial cancer on MRI images

• Published in: Biomedical engineering online Vol. 22; no. 1; pp. 1 - 17
• Main Authors: Xiong, Liu, Chen, Chunxia, Lin, Yongping, Mao, Wei, Song, Zhiyu
• Format: Journal Article
• Language: English
• Published: London BioMed Central 31.10.2023; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Algorithms; Biomaterials; Biomedical Engineering and Bioengineering; Biomedical Engineering/Biotechnology; Biotechnology; Cancer; Classification; Computer-aided diagnosis; Computer-aided medical diagnosis; Datasets; Deep learning; Diagnosis; Elliptic fitting; Endometrial cancer; Endometrium; Engineering; Gynecology; Image classification; Image segmentation; Infiltration; Machine learning; Magnetic resonance imaging; Medical imaging; Medical prognosis; Metastases; Methods; Myometrium; Obstetrics; Patients; Segmentation; Semantics; Tumors; Uterine cavity line; Uterus; China; Deep learning; Magnetic resonance imaging; Uterine cavity line; Computer-aided diagnosis
• ISSN: 1475-925X; 1475-925X
• DOI: 10.1186/s12938-023-01169-w

To classify early endometrial cancer (EC) on sagittal T2-weighted images (T2WI) by determining the depth of myometrial infiltration (MI) using a computer-aided diagnosis (CAD) method based on a multi-stage deep learning (DL) model. This study retrospectively investigated 154 patients with pathologically proven early EC at the institution between January 1, 2018, and December 31, 2020. Of these patients, 75 were in the International Federation of Gynecology and Obstetrics (FIGO) stage IA and 79 were in FIGO stage IB. An SSD-based detection model and an Attention U-net-based segmentation model were trained to select, crop, and segment magnetic resonance imaging (MRl) images. Then, an ellipse fitting algorithm was used to generate a uterine cavity line (UCL) to obtain MI depth for classification. In the independent test datasets, the uterus and tumor detection model achieves an average precision rate of 98.70% and 87.93%, respectively. Selecting the optimal MRI slices method yields an accuracy of 97.83%. The uterus and tumor segmentation model with mean IOU of 0.738 and 0.655, mean PA of 0.867 and 0.749, and mean DSC of 0.845 and 0.779, respectively. Finally, the CAD method based on the calculated MI depth reaches an accuracy of 86.9%, a sensitivity of 81.8%, and a specificity of 91.7% for early EC classification. In this study, the CAD method implements an end-to-end early EC classification and is found to be on par with radiologists in terms of performance. It is more intuitive and interpretable than previous DL-based CAD methods.